torch_robotics

Implement Differentiable Kinematics Tree & Planning Objectives in PyTorch given URDF robot models.

https://github.com/anindex/torch_robotics

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

✓
CITATION.cff file
Found CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
○
DOI references
○
Academic publication links
○
Academic email domains
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (9.1%) to scientific vocabulary

Last synced: 10 months ago · JSON representation ·

Repository

Implement Differentiable Kinematics Tree & Planning Objectives in PyTorch given URDF robot models.

Basic Info

Host: GitHub
Owner: anindex
License: mit
Language: Python
Default Branch: main
Homepage:
Size: 96.4 MB

Statistics

Stars: 38
Watchers: 2
Forks: 15
Open Issues: 0
Releases: 0

Created over 3 years ago · Last pushed almost 2 years ago

Metadata Files

Readme License Citation

TorchRobotics

This library implements differentiable robot tree from URDF or MCJF robot format, and the differentiable planning objects such as obstacle avoidance, self-collision avoidance and via point.

NOTE: torch_robotics is under heavy development and highly experimental.

Installation

Simply activate your conda/Python environment and run

azure pip install -e .

Examples

To see FK, IK of all available robot kinematics

azure python examples/forward_kinematics.py

and

azure python examples/inverse_kinematics.py

Acknowledgements

A part of this implementation is inspired from the library differentiable robot model.

Contact

If you have any questions or find any bugs, please let us know:

Citation

If you found this repository useful, please consider citing these references:

```azure @inproceedings{le2023accelerating, title={Accelerating Motion Planning via Optimal Transport}, author={Le, An T. and Chalvatzaki, Georgia and Biess, Armin and Peters, Jan}, booktitle={Advances in Neural Information Processing Systems (NeurIPS)}, year={2023} }

@article{carvalho2023motion, title={Motion planning diffusion: Learning and planning of robot motions with diffusion models}, author={Carvalho, Joao and Le, An T and Baierl, Mark and Koert, Dorothea and Peters, Jan}, journal={arXiv preprint arXiv:2308.01557}, year={2023} } ```

Owner

Name: An Thai Le
Login: anindex
Kind: user
Location: Germany
Company: Technische Universität Darmstadt

Website: https://www.ias.informatik.tu-darmstadt.de/Team/AnThaiLe
Twitter: an_thai_le
Repositories: 3
Profile: https://github.com/anindex

Citation (CITATION.cff)

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- family-names: "Le"
  given-names: "An"
  affiliation: "TU Darmstadt"
- family-names: "Carvalho"
  given-names: "Joao"
  affiliation: "TU Darmstadt"
title: "torch_robotics"
version: 0.1.0
date-released: 15-10-23
url: "https://github.com/anindex/torch_robotics"

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Open Source Science